This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Abstract - #308007
Title: WITHDRAWN: Using a Selective Robust Bayes Classifier to Predict Survival from Sudden Cardiac Arrest in a Study with Missing Attributes
Author(s): Subhashish Chakravarty and Kyndaron Reinier and Carmen Teodorescu and Audrey Evanado and Ronald Mariani and Jo Navarro and Karen Gunson and Jonathan Jui and Sumeet Chugh
Companies:
Address:
Keywords: sudden cardiac arrest ; robust Bayes classifier
Abstract:

The Oregon Sudden Unexpected Death Study, a population-based study of sudden cardiac arrest (SCA) in Portland, Oregon, uses attributes from detailed first responder reports and medical records to predict survival from SCA. Like most population based studies, we have missing attribute data. In this analysis, we employ a selective robust Bayes classifier (RBC), which makes no assumption about the missing data pattern. Data collected from 2002-2007 are used to train a selective RBC based on information gain ratio to predict SCA survivors in 2007-2008. Information gain ratio is first used to select a subset of attributes relevant to survival. A selective RBC is then constructed from this subset by adding performance-improving attributes using a best first search method. We compare the performance of the classifier with a logistic regression model predicting survival from complete data.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.